Mapping of Pollution Distribution for Electric Power System Based on Satellite Remote Sensing

In recent years, the frequent fouling accidents have posed a serious threat to people’s life and property safety. Owing wide distribution of pollution sources variable meteorological factors, it is very time-consuming labor-intensive task map using traditional methods. this work, study on mapping based satellite remote sensing carried out in Yunnan Province, China, as an example. Several machine learning methods (e.g. K-nearest neighbor, support vector machine) are used analyze effects conditions such multiple air data levels. The results indicate that ensemble model has highest accuracy 72.32% application. new classifier 5,506 more pixels most severe level than map. Last, sensing-based manual measurement-based were combined with corresponding experience weight obtain weighted